Diagnostics最新文献

{"title":"Fully Automated Photoplethysmography-Based Wearable Atrial Fibrillation Screening in a Hospital Setting.","authors":"Khaled Abdelhamid, Pamela Reissenberger, Diana Piper, Nicole Koenig, Bianca Hoelz, Julia Schlaepfer, Simone Gysler, Helena McCullough, Sebastian Ramin-Wright, Anna-Lena Gabathuler, Jahnvi Khandpur, Milene Meier, Jens Eckstein","doi":"10.3390/diagnostics15101233","DOIUrl":"10.3390/diagnostics15101233","url":null,"abstract":"<p><p><b>Background/Objectives</b>: Atrial fibrillation (AF) remains a major risk factor for stroke. It is often asymptomatic and paroxysmal, making it difficult to detect with conventional electrocardiography (ECG). While photoplethysmography (PPG)-based devices like smartwatches have demonstrated efficacy in detecting AF, they are rarely integrated into hospital infrastructure. The study aimed to establish a seamless system for real-time AF screening in hospitalized high-risk patients using a wrist-worn PPG device integrated into a hospital's data infrastructure. <b>Methods</b>: In this investigator-initiated prospective clinical trial conducted at the University Hospital Basel, patients with a CHA₂DS₂-VASc score ≥ 2 and no history of AF received a wristband equipped with a PPG sensor for continuous monitoring during their hospital stay. The PPG data were automatically transmitted, analyzed, stored, and visualized. Upon detection of an absolute arrhythmia (AA) in the PPG signal, a Holter ECG was administered. <b>Results</b>: The analysis encompassed 346 patients (mean age 72 ± 10 years, 175 females (50.6%), mean CHA₂DS₂-VASc score 3.5 ± 1.3)). The mean monitoring duration was 4.3 ± 4.4 days. AA in the PPG signal was detected in twelve patients (3.5%, CI: 1.5-5.4%), with most cases identified within 24 h (<i>p</i> = 0.004). There was a 1.3 times higher AA burden during the nighttime compared to daytime (<i>p</i> = 0.03). Compliance was high (304/346, 87.9%). No instances of AF were confirmed in the nine patients undergoing Holter ECG. <b>Conclusions</b>: This study successfully pioneered an automated infrastructure for AF screening in hospitalized patients through the use of wrist-worn PPG devices. This implementation allowed for real-time data visualization and intervention in the form of a Holter ECG. The high compliance and early AA detection achieved in this study underscore the potential and relevance of this novel infrastructure in clinical practice.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12110636/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Systematic Review and Meta-Analysis of Ocular and Periocular Basal Cell Carcinoma with First-Time Description of Dermoscopic and Reflectance Confocal Microscopy Features of Caruncle Basal Cell Carcinoma.","authors":"Martina Caviglia, Shaniko Kaleci, Pasquale Frascione, Miram Teoli, Maria Concetta Fargnoli, Giovanni Pellacani, Victor Desmond Mandel","doi":"10.3390/diagnostics15101244","DOIUrl":"10.3390/diagnostics15101244","url":null,"abstract":"<p><p><b>Background</b>: Basal cell carcinoma (BCC) of the ocular and periocular region is characterized by a painless progressive extension. An early diagnosis can limit the extent of facial tissue involvement and subsequent resection resulting in better cosmetic and functional results. <b>Objectives</b>: The aim is to provide the largest and most up-to-date overview of ocular and periocular BCCs. We also reported the first case of caruncle BCC investigated by dermoscopy and reflectance confocal microscopy (RCM). <b>Methods</b>: A systematic review and meta-analysis (Prospero ID CRD583032) were carried out by searching PUBMED-MEDLINE, including all articles with a full-text English version and with BCCs in eyelids, medial and lateral canthus, caruncle, conjunctiva, and orbit. The following data were collected: authors, year, title and type of publication, medical specialization, number, sex, age and comorbidities of the patients, anatomic localization of the disease, clinical and dermoscopic aspect, histological examination, and treatment. <b>Results</b>: We identified 731 articles through a database search, of which 236 articles matched our inclusion criteria. A total of 71.730 patients with ocular and periocular BCCs were included in the present study, and all data collected were reported in a dataset. Most of the articles included were described by ophthalmologists (67.5%), dermatologists (11.2%), or plastic surgeons (5.6%). The proportional meta-analysis revealed varying significance and heterogeneity for each type of study included. <b>Conclusions</b>: BCC more frequently affects the lower eyelid. The most common BCC subtype of ocular and periocular area is the nodular form. Limited data are available concerning the application of dermoscopy and RCM in this area. RCM may be particularly useful for early diagnosis, mapping, and treatment monitoring of ocular and periocular BCCs. Surgery still remains the first-choice treatment.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109886/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating Dynamic Red Blood Cell Distribution Width Monitoring and β-Blocker Therapy for Mortality Prediction in Intensive Care Unit Cardiomyopathy Patients: A Bayesian Multivariate Joint Model and Machine Learning Study.","authors":"Si Chen, Rui Nie, Yi Wang, Haoran Guo, Yan Wang, Haixia Luan, Xiaoli Zeng, Hui Yuan","doi":"10.3390/diagnostics15101236","DOIUrl":"10.3390/diagnostics15101236","url":null,"abstract":"&lt;p&gt;&lt;p&gt;&lt;b&gt;Background/Objective:&lt;/b&gt; Cardiomyopathy is a key cause of cardiovascular mortality in critically ill patients. Although red blood cell distribution width (RDW) is recognized as a potential prognostic biomarker, its variations during ICU admission and its interaction with treatments such as β-blockers are not well understood across different cardiomyopathy subtypes. To assess the prognostic significance of RDW dynamics and their interaction with β-blocker therapy in predicting 365-day mortality among ICU patients with dilated, hypertrophic, and restrictive cardiomyopathy, utilizing longitudinal data and advanced modeling techniques. &lt;b&gt;Methods:&lt;/b&gt; A retrospective analysis was conducted on 317 cardiomyopathy patients from the MIMIC-IV database. Their RDW dynamics were assessed over their ICU stay. Cox regression (including time-dependent Cox models) and logistic regression identified independent mortality risk factors. Key predictors were identified using Least absolute shrinkage and selection operator (LASSO) regression and the Boruta algorithm. Restricted cubic splines (RCSs) were used to examine nonlinear relationships. Machine learning models were used to evaluate predictive performance, with SHapley Additive Explanations (SHAP) and tree-based feature selection identifying influential variables. Repeated-measures ANOVA was used to analyze RDW trends and β-blocker associations. A Bayesian multivariate joint model (BMJM) integrated RDW dynamics and β-blocker therapy, incorporating repeated measures and survival outcomes. &lt;b&gt;Results:&lt;/b&gt; RDW was an independent predictor of 365-day mortality (HR = 1.14, 95% CI: 1.01-1.29, &lt;i&gt;p&lt;/i&gt; = 0.03), alongside the systemic immune-inflammation index (SII) (HR = 1.01, 95% CI: 1.00-1.01, &lt;i&gt;p&lt;/i&gt; = 0.03), whereas β-blockers significantly reduced mortality risk (HR = 0.2, 95% CI: 0.1-0.39, &lt;i&gt;p&lt;/i&gt; &lt; 0.001). Comparative analysis demonstrated that RDW exhibited greater predictive value over the aggregate index of systemic inflammation (AISI), systemic inflammation response index (SIRI), and SII. Machine learning identified logistic classification as the best predictive model (AUC = 0.811), with SHAP and tree-based selection confirming RDW and β-blockers as key predictors. A repeated-measures ANOVA revealed a significant interaction between RDW and β-blocker use (F = 6.65, &lt;i&gt;p&lt;/i&gt; &lt; 0.0001), with β-blockers lowering RDW levels. The BMJM demonstrated strong predictive performance (AUC = 0.80). The patient-specific BMJM indicated that discontinuing β-blockers increased the risk of mortality, while initiating β-blockers reduced it. &lt;b&gt;Conclusions:&lt;/b&gt; This study highlights dynamic RDW monitoring and β-blocker therapy as strong predictors of 365-day mortality in ICU-admitted cardiomyopathy patients. The BMJM enables personalized risk assessment by integrating longitudinal biomarker data. These findings support RDW as a dynamic biomarker and advocate for its integration into personalized treatment strategies","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109794/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Predictors and Risk Factors of Gleason Score Upgrade: A Retrospective Cohort Analysis.","authors":"Carmine Sciorio, Riccardo Giannella, Lorenzo Romano, Benito Fabio Mirto, Antonio Di Girolamo, Antonio Ruffo, Giuseppe Romeo, Fabio Esposito, Felice Crocetto, Luigi Napolitano, Raffaele Balsamo, Francesco Trama, Francesco Bottone, Carmelo Quattrone, Vittorio Imperatore, Lorenzo Spirito","doi":"10.3390/diagnostics15101238","DOIUrl":"10.3390/diagnostics15101238","url":null,"abstract":"<p><p><b>Background:</b> In prostate cancer (PCa) patients, discrepancies between biopsy-assigned Gleason Scores and those determined from surgical specimens are frequently reported. This phenomenon, known as Gleason score upgrade (GSU), can have significant clinical implications. This work aims to understand the factors contributing to GSU for refining prostate cancer management strategies. <b>Methods:</b> Data from 779 patients diagnosed with histologically confirmed PCa who underwent robot-assisted radical prostatectomy at a single tertiary care institution between January 2005 and December 2020 were examined. <b>Results:</b> In the univariable setting, 5-alpha reductase inhibitor (5-ARI) use was associated with a higher percentage of upgrading (42.3% vs. 30.4% among non-users; <i>p</i> = 0.03942). A more advanced pathological T stage (<i>p</i> = 0.01114) and lymph node positivity (<i>p</i> < 0.00001) correlated significantly with GSU. In the logistic regression model, advanced pathological stage increased the odds more than twofold (OR = 2.807, <i>p</i> = 0.00135). 5-ARI use was associated with notably higher odds of upgrading (OR = 3.809, <i>p</i> = 0.00004). Younger age slightly increased the likelihood of GSU (OR = 0.951 per year increase in age, <i>p</i> = 0.01101). <b>Conclusions:</b> Younger age, advanced pathological stage, and the use of 5-alpha reductase inhibitors were identified as significant predictors of GSU.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12110525/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting Clinical Response to Monoclonal TNF Inhibitors in Rheumatoid Arthritis: A Transcriptomic Approach Based on Transmembrane TNF Reverse Signaling and Nrf2 Activation.","authors":"Katy Diallo, Yannick Degboé, Michel Baron, Anaïs Bellin-Robert, Jean-Frédéric Boyer, Adeline Ruyssen-Witrand, Arnaud Constantin, Benjamin Rauwel, Alain Cantagrel, Jean-Luc Davignon","doi":"10.3390/diagnostics15101232","DOIUrl":"10.3390/diagnostics15101232","url":null,"abstract":"<p><p>(1) <b>Background</b>: TNF inhibitors (TNFis) have revolutionized the treatment of rheumatoid arthritis (RA). However, 30-40% of RA patients do not respond adequately to those biologics. In addition to neutralizing soluble TNF, TNFis have the ability to bind the transmembrane form of TNF, tmTNF. Importantly, tmTNF can act itself as a receptor that induces \"Reverse Signaling\" (RS) in cells. We previously showed that certolizumab, a Fab' TNFi, activates RS in human primary monocytes, at least in part through the transcription factor Nrf2 that is known to regulate the expression of genes involved in anti-inflammatory response and oxidative stress. (2) <b>Methods</b>: Here, we have developed an assay for the prediction of clinical response of RA patients to TNF inhibitors. This assay is based on mRNA quantitation of CD36 activation and of six genes induced by Nrf2 following tmTNF RS in fresh monocytes. (3) <b>Results</b>: We could predict the response to anti-TNF monoclonal antibodies (mAbs) with 93.3% accuracy. However, our method was not suitable for the prediction of the response to TNF soluble receptor etanercept. (4) <b>Conclusions</b>: We have developed a rather simple, short-term test that can be standardized. Predicting the response to TNF mAbs will help physicians offer the best available treatment and provide patients with personalized medicine.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109967/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prevalence of Psychiatric and Addictive Disorders in Patients with Psoriasis: A Cross-Sectional Study.","authors":"Daciana Elena Brănișteanu, Roxana Paraschiva Ciobanu, Daniel Constantin Branisteanu, Cristina Colac-Boțoc, Antonia-Elena Huțanu, Cătălina-Anca Munteanu, Rares Stamate, George Brănișteanu, Catalina Ioana Onu-Branisteanu, Mihaela Paula Toader, Elena Porumb-Andrese","doi":"10.3390/diagnostics15101231","DOIUrl":"10.3390/diagnostics15101231","url":null,"abstract":"<p><p><b>Background/Objectives:</b> Psoriasis is a chronic inflammatory skin disease increasingly linked to psychiatric and behavioral comorbidities, including depression, anxiety, and substance use disorders. Shared inflammatory pathways, including elevated IL-6, TNF-α, and IL-17, may link psoriasis with psychiatric disorders such as depression and anxiety. The bidirectional interaction between systemic inflammation and mental health may exacerbate the disease burden and affect treatment outcomes. The objective of this study was to determine the prevalence of psychiatric and behavioral comorbidities in patients with psoriasis and to explore potential demographic and clinical correlations. Assessing these correlations contributes to a better understanding of the mental health status of psoriasis patients, potentially influencing both therapeutic efficacy and quality of life. <b>Methods:</b> We conducted a cross-sectional observational study on 316 patients with clinically and histopathologically confirmed psoriasis, evaluated between January 2021 and March 2025 at the Clinical Railway Hospital in Iași, Romania. Psychiatric and behavioral comorbidities were assessed through clinical interviews, medical record reviews, and standardized tools including AUDIT-C, Fagerström Test for Nicotine Dependence, and the Binge Eating Scale. Psoriasis severity was evaluated using the Psoriasis Area and Severity Index (PASI). <b>Results:</b> Of 316 participants, 88 (27.8%) had psychiatric/behavioral comorbidities. The most frequent conditions were tobacco use disorder (11.1% overall; 39.8% among comorbid patients), alcohol use disorder (9.2%; 32.9%), binge eating (7.9%; 28.4%), anxiety (6.3%; 22.7%), and depression (4.1%; 14.8%). Additional diagnoses included personality disorders, dementia, PTSD, and sleep disorders. <b>Conclusions:</b> Psychiatric and behavioral comorbidities, particularly substance use disorders, are relatively common in patients with psoriasis. These findings support the need for regular mental health screening and integrated care approaches in psoriasis management.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12110098/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Incidence of Adverse Events in Adults Undergoing Procedural Sedation with Propofol Administered by Non-Anesthetists: A Systematic Review and Meta-Analysis.","authors":"Flavia Pigò, Matteo Gottin, Rita Conigliaro","doi":"10.3390/diagnostics15101234","DOIUrl":"10.3390/diagnostics15101234","url":null,"abstract":"<p><p><b>Background/Objectives:</b> The administration of propofol without an anesthesiologist (NAAP) during endoscopic procedures is generally considered safe. However, the available data remain limited and fragmented due to legal constraints. This systematic review and meta-analysis aimed to evaluate the incidence of adverse events in adults undergoing procedural sedation with NAAP. <b>Methods:</b> A comprehensive search was conducted in three electronic databases (MEDLINE, EMBASE, and the Cochrane Library) for studies published between 2010 and 2023. Eligible studies included randomized controlled trials and observational studies that reported predefined adverse events in adult patients receiving NAAP for procedural sedation. The analysis encompassed various types of endoscopic procedures and sedation protocols, including both balanced sedation and propofol monotherapy. Clinical heterogeneity was assessed by comparing patient characteristics, sedation methods, and outcome measures across studies. A random effects model was used for the meta-analysis, with results presented as estimated incidence rates. Subgroup analyses were conducted based on the hypoxia severity, sedation approach, and procedure type. <b>Results:</b> The search yielded 2963 records, of which 73 studies met the inclusion criteria, covering a total of 967,238 procedural sedations. Hypoxia was the most frequently reported adverse event, occurring in 40‱ of cases, followed by hypotension (38‱) and bradycardia (9‱). Severe adverse events requiring emergency intervention were rare, with an incidence of 0.12‱. The subgroup analysis indicated a low occurrence (6‱) of severe desaturation (SpO₂ < 80%) and no significant differences in adverse event rates between balanced propofol sedation and propofol-only sedation. However, advanced endoscopic procedures (EUS, ERCP, PEG, enteroscopy, EMR/ESD) were associated with a higher risk of hypoxia (10% vs. 26‱; <i>p</i> < 0.00001) and major complications (3.1‱ vs. 0.1‱; <i>p</i> = 0.015) compared to diagnostic procedures. <b>Conclusions:</b> NAAP-based procedural sedation appears to be generally safe. While the minor adverse event rates vary depending on the sedation regimen and procedure type, major complications remain exceptionally rare.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12110594/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pancreatic Comorbidities in Pediatric Celiac Disease: Exocrine Pancreatic Insufficiency, Pancreatitis, and Diabetes Mellitus.","authors":"Dimitri Poddighe","doi":"10.3390/diagnostics15101243","DOIUrl":"10.3390/diagnostics15101243","url":null,"abstract":"<p><p>Celiac disease (CD) is a chronic and immune-mediated disorder triggered by the ingestion of gluten in some genetically predisposed individuals. CD can be associated with extra-gastrointestinal manifestations and diseases affecting several organs. In this review, the aim is to analyze and discuss the pancreatic alterations and/or comorbidities that could arise in the context of pediatric CD. Exocrine pancreatic insufficiency (EPI) can be observed in a variable fraction (up to 30%) of children diagnosed with CD at the diagnosis; indeed, it usually resolves after the implementation of a gluten-free diet (GFD). The main pathophysiological mechanisms of EPI could be represented by the impaired pattern of gastrointestinal hormones in CD patients. Conversely, pancreatitis seems to be a very rare comorbidity in CD children, since very few cases have been described in children. Therefore, there is no evidence that pancreatitis (including autoimmune forms) represents a relevant comorbidity in pediatric CD. Type 1 diabetes mellitus (T1DM) is a well-known and frequent comorbidity in CD children. The main determinant of this epidemiological association is the common HLA-related predisposing background, even if other (non-HLA-related) genetic and environmental factors (viruses, gut microbiome, and others) are likely to be also implicated in the development of both these autoimmune diseases. T1DM children with concomitant CD may experience specific challenges in the adherence to GFD, which has no negative impact on the glycemic and, in general, metabolic control of diabetes, if it is properly implemented and followed up.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12110372/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Deep Learning for Survival Prediction in Brain Metastases Using Multimodal MRI and Clinical Data.","authors":"Cristian Constantin Volovăț, Călin Gheorghe Buzea, Diana-Ioana Boboc, Mădălina-Raluca Ostafe, Maricel Agop, Lăcrămioara Ochiuz, Ștefan Lucian Burlea, Dragoș Ioan Rusu, Laurențiu Bujor, Dragoș Teodor Iancu, Simona Ruxandra Volovăț","doi":"10.3390/diagnostics15101242","DOIUrl":"10.3390/diagnostics15101242","url":null,"abstract":"<p><p><b>Background:</b> Survival prediction in patients with brain metastases remains a major clinical challenge, where timely and individualized prognostic estimates are critical for guiding treatment strategies and patient counseling. <b>Methods:</b> We propose a novel hybrid deep learning framework that integrates volumetric MRI-derived imaging biomarkers with structured clinical and demographic data to predict overall survival time. Our dataset includes 148 patients from three institutions, featuring expert-annotated segmentations of enhancing tumors, necrosis, and peritumoral edema. Two convolutional neural network backbones-ResNet-50 and EfficientNet-B0-were fused with fully connected layers processing tabular data. Models were trained using mean squared error loss and evaluated through stratified cross-validation and an independent held-out test set. <b>Results:</b> The hybrid model based on EfficientNet-B0 achieved state-of-the-art performance, attaining an R² score of 0.970 and a mean absolute error of 3.05 days on the test set. Permutation feature importance highlighted edema-to-tumor ratio and enhancing tumor volume as the most informative predictors. Grad-CAM visualizations confirmed the model's attention to anatomically and clinically relevant regions. Performance consistency across validation folds confirmed the framework's robustness and generalizability. <b>Conclusions:</b> This study demonstrates that multimodal deep learning can deliver accurate, explainable, and clinically actionable survival predictions in brain metastases. The proposed framework offers a promising foundation for integration into real-world oncology workflows to support personalized prognosis and informed therapeutic decision-making.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109748/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction and Stage Classification of Pressure Ulcers in Intensive Care Patients by Machine Learning.","authors":"Mürsel Kahveci, Levent Uğur","doi":"10.3390/diagnostics15101239","DOIUrl":"10.3390/diagnostics15101239","url":null,"abstract":"<p><p><b>Background/Objective:</b> Pressure ulcers are a serious clinical problem associated with high morbidity, mortality and healthcare costs, especially in intensive care unit (ICU) patients. Existing risk assessment tools, such as the Braden Score, are often inadequate in ICU patients and have poor discriminatory power between classes. This increases the need for more sensitive, predictive and integrative systems. The aim of this study was to classify pressure ulcer stages (Stages I-IV) with high accuracy using machine learning algorithms using demographic, clinical and laboratory data of ICU patients and to evaluate the model performance at a level that can be integrated into clinical decision support systems. <b>Methods:</b> A total of 200 patients hospitalized in the ICU were included in the study. Using demographic, clinical and laboratory data of the patients, six different machine learning algorithms (SVM, KNN, ANN, Decision Tree, Naive Bayes and Discriminant Analysis) were used for classification. The models were evaluated using confusion matrices, ROC-AUC analyses and metrics such as class-based sensitivity and error rate. <b>Results:</b> SVM, KNN and ANN models showed the highest success in classifying pressure ulcer stages, achieving 99% overall accuracy and excellent performance with AUC = 1.00. Variables such as Braden score, albumin and CRP levels contributed significantly to model performance. ROC curves showed that the models provided strong discrimination between classes. Key predictors of pressure ulcer severity included prolonged ICU stay (<i>p</i> < 0.001), low albumin (Stage I: 3.4 ± 0.5 g/dL vs. Stage IV: 2.4 ± 0.8 g/dL; <i>p</i> < 0.001) and high CRP (Stage I: 28 mg/L vs. Stage IV: 142 mg/L; <i>p</i> < 0.001). <b>Conclusions:</b> This study shows that machine learning algorithms offer high accuracy and generalization potential in pressure ulcer classification. In particular, the effectiveness of algorithms such as SVM, ANN and KNN in detecting early-stage ulcers is promising in terms of integration into clinical decision support systems. In future studies, the clinical validity of the model should be increased with multicenter datasets and visual-data-based hybrid models.</p>","PeriodicalId":11225,"journal":{"name":"Diagnostics","volume":"15 10","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109807/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144157344","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}